versae commited on
Commit
c52db70
1 Parent(s): 4be463f

Fixes tokenizer and ggml models

Browse files
added_tokens.json ADDED
@@ -0,0 +1,145 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|extratoken_100|>": 50356,
3
+ "<|extratoken_101|>": 50357,
4
+ "<|extratoken_102|>": 50358,
5
+ "<|extratoken_103|>": 50359,
6
+ "<|extratoken_104|>": 50360,
7
+ "<|extratoken_105|>": 50361,
8
+ "<|extratoken_106|>": 50362,
9
+ "<|extratoken_107|>": 50363,
10
+ "<|extratoken_108|>": 50364,
11
+ "<|extratoken_109|>": 50365,
12
+ "<|extratoken_10|>": 50266,
13
+ "<|extratoken_110|>": 50366,
14
+ "<|extratoken_111|>": 50367,
15
+ "<|extratoken_112|>": 50368,
16
+ "<|extratoken_113|>": 50369,
17
+ "<|extratoken_114|>": 50370,
18
+ "<|extratoken_115|>": 50371,
19
+ "<|extratoken_116|>": 50372,
20
+ "<|extratoken_117|>": 50373,
21
+ "<|extratoken_118|>": 50374,
22
+ "<|extratoken_119|>": 50375,
23
+ "<|extratoken_11|>": 50267,
24
+ "<|extratoken_120|>": 50376,
25
+ "<|extratoken_121|>": 50377,
26
+ "<|extratoken_122|>": 50378,
27
+ "<|extratoken_123|>": 50379,
28
+ "<|extratoken_124|>": 50380,
29
+ "<|extratoken_125|>": 50381,
30
+ "<|extratoken_126|>": 50382,
31
+ "<|extratoken_127|>": 50383,
32
+ "<|extratoken_128|>": 50384,
33
+ "<|extratoken_129|>": 50385,
34
+ "<|extratoken_12|>": 50268,
35
+ "<|extratoken_130|>": 50386,
36
+ "<|extratoken_131|>": 50387,
37
+ "<|extratoken_132|>": 50388,
38
+ "<|extratoken_133|>": 50389,
39
+ "<|extratoken_134|>": 50390,
40
+ "<|extratoken_135|>": 50391,
41
+ "<|extratoken_136|>": 50392,
42
+ "<|extratoken_137|>": 50393,
43
+ "<|extratoken_138|>": 50394,
44
+ "<|extratoken_139|>": 50395,
45
+ "<|extratoken_13|>": 50269,
46
+ "<|extratoken_140|>": 50396,
47
+ "<|extratoken_141|>": 50397,
48
+ "<|extratoken_142|>": 50398,
49
+ "<|extratoken_143|>": 50399,
50
+ "<|extratoken_14|>": 50270,
51
+ "<|extratoken_15|>": 50271,
52
+ "<|extratoken_16|>": 50272,
53
+ "<|extratoken_17|>": 50273,
54
+ "<|extratoken_18|>": 50274,
55
+ "<|extratoken_19|>": 50275,
56
+ "<|extratoken_1|>": 50257,
57
+ "<|extratoken_20|>": 50276,
58
+ "<|extratoken_21|>": 50277,
59
+ "<|extratoken_22|>": 50278,
60
+ "<|extratoken_23|>": 50279,
61
+ "<|extratoken_24|>": 50280,
62
+ "<|extratoken_25|>": 50281,
63
+ "<|extratoken_26|>": 50282,
64
+ "<|extratoken_27|>": 50283,
65
+ "<|extratoken_28|>": 50284,
66
+ "<|extratoken_29|>": 50285,
67
+ "<|extratoken_2|>": 50258,
68
+ "<|extratoken_30|>": 50286,
69
+ "<|extratoken_31|>": 50287,
70
+ "<|extratoken_32|>": 50288,
71
+ "<|extratoken_33|>": 50289,
72
+ "<|extratoken_34|>": 50290,
73
+ "<|extratoken_35|>": 50291,
74
+ "<|extratoken_36|>": 50292,
75
+ "<|extratoken_37|>": 50293,
76
+ "<|extratoken_38|>": 50294,
77
+ "<|extratoken_39|>": 50295,
78
+ "<|extratoken_3|>": 50259,
79
+ "<|extratoken_40|>": 50296,
80
+ "<|extratoken_41|>": 50297,
81
+ "<|extratoken_42|>": 50298,
82
+ "<|extratoken_43|>": 50299,
83
+ "<|extratoken_44|>": 50300,
84
+ "<|extratoken_45|>": 50301,
85
+ "<|extratoken_46|>": 50302,
86
+ "<|extratoken_47|>": 50303,
87
+ "<|extratoken_48|>": 50304,
88
+ "<|extratoken_49|>": 50305,
89
+ "<|extratoken_4|>": 50260,
90
+ "<|extratoken_50|>": 50306,
91
+ "<|extratoken_51|>": 50307,
92
+ "<|extratoken_52|>": 50308,
93
+ "<|extratoken_53|>": 50309,
94
+ "<|extratoken_54|>": 50310,
95
+ "<|extratoken_55|>": 50311,
96
+ "<|extratoken_56|>": 50312,
97
+ "<|extratoken_57|>": 50313,
98
+ "<|extratoken_58|>": 50314,
99
+ "<|extratoken_59|>": 50315,
100
+ "<|extratoken_5|>": 50261,
101
+ "<|extratoken_60|>": 50316,
102
+ "<|extratoken_61|>": 50317,
103
+ "<|extratoken_62|>": 50318,
104
+ "<|extratoken_63|>": 50319,
105
+ "<|extratoken_64|>": 50320,
106
+ "<|extratoken_65|>": 50321,
107
+ "<|extratoken_66|>": 50322,
108
+ "<|extratoken_67|>": 50323,
109
+ "<|extratoken_68|>": 50324,
110
+ "<|extratoken_69|>": 50325,
111
+ "<|extratoken_6|>": 50262,
112
+ "<|extratoken_70|>": 50326,
113
+ "<|extratoken_71|>": 50327,
114
+ "<|extratoken_72|>": 50328,
115
+ "<|extratoken_73|>": 50329,
116
+ "<|extratoken_74|>": 50330,
117
+ "<|extratoken_75|>": 50331,
118
+ "<|extratoken_76|>": 50332,
119
+ "<|extratoken_77|>": 50333,
120
+ "<|extratoken_78|>": 50334,
121
+ "<|extratoken_79|>": 50335,
122
+ "<|extratoken_7|>": 50263,
123
+ "<|extratoken_80|>": 50336,
124
+ "<|extratoken_81|>": 50337,
125
+ "<|extratoken_82|>": 50338,
126
+ "<|extratoken_83|>": 50339,
127
+ "<|extratoken_84|>": 50340,
128
+ "<|extratoken_85|>": 50341,
129
+ "<|extratoken_86|>": 50342,
130
+ "<|extratoken_87|>": 50343,
131
+ "<|extratoken_88|>": 50344,
132
+ "<|extratoken_89|>": 50345,
133
+ "<|extratoken_8|>": 50264,
134
+ "<|extratoken_90|>": 50346,
135
+ "<|extratoken_91|>": 50347,
136
+ "<|extratoken_92|>": 50348,
137
+ "<|extratoken_93|>": 50349,
138
+ "<|extratoken_94|>": 50350,
139
+ "<|extratoken_95|>": 50351,
140
+ "<|extratoken_96|>": 50352,
141
+ "<|extratoken_97|>": 50353,
142
+ "<|extratoken_98|>": 50354,
143
+ "<|extratoken_99|>": 50355,
144
+ "<|extratoken_9|>": 50265
145
+ }
ggml-model-f16.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d9217b0e20b493fb01ccb2a5a1b3e94cd31119c487fb6eb0b0807787e5510d9
3
- size 12104024635
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8672f372dae6bb7660f070355adb44dbb35747746525192b89a24466aabebbb4
3
+ size 12104027673
ggml-model-f32.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5857adc1096935e584fb3b9b2d7134016ebb24fe64d1bc54985aecdbc04eb46
3
- size 24204067387
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:19ca96d654991182a4a2e1aace9465fdddf1a2928d1e549518bd9fb33d5c0bcd
3
+ size 24204070425
special_tokens_map.json CHANGED
@@ -1 +1,23 @@
1
- {"bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "unk_token": "<|endoftext|>"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
tokenizer.json CHANGED
@@ -9,8 +9,1295 @@
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
- "normalized": false,
13
  "special": true
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
14
  }
15
  ],
16
  "normalizer": null,
9
  "single_word": false,
10
  "lstrip": false,
11
  "rstrip": false,
12
+ "normalized": true,
13
  "special": true
14
+ },
15
+ {
16
+ "id": 50257,
17
+ "content": "<|extratoken_1|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": true,
22
+ "special": false
23
+ },
24
+ {
25
+ "id": 50258,
26
+ "content": "<|extratoken_2|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": true,
31
+ "special": false
32
+ },
33
+ {
34
+ "id": 50259,
35
+ "content": "<|extratoken_3|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": true,
40
+ "special": false
41
+ },
42
+ {
43
+ "id": 50260,
44
+ "content": "<|extratoken_4|>",
45
+ "single_word": false,
46
+ "lstrip": false,
47
+ "rstrip": false,
48
+ "normalized": true,
49
+ "special": false
50
+ },
51
+ {
52
+ "id": 50261,
53
+ "content": "<|extratoken_5|>",
54
+ "single_word": false,
55
+ "lstrip": false,
56
+ "rstrip": false,
57
+ "normalized": true,
58
+ "special": false
59
+ },
60
+ {
61
+ "id": 50262,
62
+ "content": "<|extratoken_6|>",
63
+ "single_word": false,
64
+ "lstrip": false,
65
+ "rstrip": false,
66
+ "normalized": true,
67
+ "special": false
68
+ },
69
+ {
70
+ "id": 50263,
71
+ "content": "<|extratoken_7|>",
72
+ "single_word": false,
73
+ "lstrip": false,
74
+ "rstrip": false,
75
+ "normalized": true,
76
+ "special": false
77
+ },
78
+ {
79
+ "id": 50264,
80
+ "content": "<|extratoken_8|>",
81
+ "single_word": false,
82
+ "lstrip": false,
83
+ "rstrip": false,
84
+ "normalized": true,
85
+ "special": false
86
+ },
87
+ {
88
+ "id": 50265,
89
+ "content": "<|extratoken_9|>",
90
+ "single_word": false,
91
+ "lstrip": false,
92
+ "rstrip": false,
93
+ "normalized": true,
94
+ "special": false
95
+ },
96
+ {
97
+ "id": 50266,
98
+ "content": "<|extratoken_10|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": true,
103
+ "special": false
104
+ },
105
+ {
106
+ "id": 50267,
107
+ "content": "<|extratoken_11|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": true,
112
+ "special": false
113
+ },
114
+ {
115
+ "id": 50268,
116
+ "content": "<|extratoken_12|>",
117
+ "single_word": false,
118
+ "lstrip": false,
119
+ "rstrip": false,
120
+ "normalized": true,
121
+ "special": false
122
+ },
123
+ {
124
+ "id": 50269,
125
+ "content": "<|extratoken_13|>",
126
+ "single_word": false,
127
+ "lstrip": false,
128
+ "rstrip": false,
129
+ "normalized": true,
130
+ "special": false
131
+ },
132
+ {
133
+ "id": 50270,
134
+ "content": "<|extratoken_14|>",
135
+ "single_word": false,
136
+ "lstrip": false,
137
+ "rstrip": false,
138
+ "normalized": true,
139
+ "special": false
140
+ },
141
+ {
142
+ "id": 50271,
143
+ "content": "<|extratoken_15|>",
144
+ "single_word": false,
145
+ "lstrip": false,
146
+ "rstrip": false,
147
+ "normalized": true,
148
+ "special": false
149
+ },
150
+ {
151
+ "id": 50272,
152
+ "content": "<|extratoken_16|>",
153
+ "single_word": false,
154
+ "lstrip": false,
155
+ "rstrip": false,
156
+ "normalized": true,
157
+ "special": false
158
+ },
159
+ {
160
+ "id": 50273,
161
+ "content": "<|extratoken_17|>",
162
+ "single_word": false,
163
+ "lstrip": false,
164
+ "rstrip": false,
165
+ "normalized": true,
166
+ "special": false
167
+ },
168
+ {
169
+ "id": 50274,
170
+ "content": "<|extratoken_18|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": true,
175
+ "special": false
176
+ },
177
+ {
178
+ "id": 50275,
179
+ "content": "<|extratoken_19|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": true,
184
+ "special": false
185
+ },
186
+ {
187
+ "id": 50276,
188
+ "content": "<|extratoken_20|>",
189
+ "single_word": false,
190
+ "lstrip": false,
191
+ "rstrip": false,
192
+ "normalized": true,
193
+ "special": false
194
+ },
195
+ {
196
+ "id": 50277,
197
+ "content": "<|extratoken_21|>",
198
+ "single_word": false,
199
+ "lstrip": false,
200
+ "rstrip": false,
201
+ "normalized": true,
202
+ "special": false
203
+ },
204
+ {
205
+ "id": 50278,
206
+ "content": "<|extratoken_22|>",
207
+ "single_word": false,
208
+ "lstrip": false,
209
+ "rstrip": false,
210
+ "normalized": true,
211
+ "special": false
212
+ },
213
+ {
214
+ "id": 50279,
215
+ "content": "<|extratoken_23|>",
216
+ "single_word": false,
217
+ "lstrip": false,
218
+ "rstrip": false,
219
+ "normalized": true,
220
+ "special": false
221
+ },
222
+ {
223
+ "id": 50280,
224
+ "content": "<|extratoken_24|>",
225
+ "single_word": false,
226
+ "lstrip": false,
227
+ "rstrip": false,
228
+ "normalized": true,
229
+ "special": false
230
+ },
231
+ {
232
+ "id": 50281,
233
+ "content": "<|extratoken_25|>",
234
+ "single_word": false,
235
+ "lstrip": false,
236
+ "rstrip": false,
237
+ "normalized": true,
238
+ "special": false
239
+ },
240
+ {
241
+ "id": 50282,
242
+ "content": "<|extratoken_26|>",
243
+ "single_word": false,
244
+ "lstrip": false,
245
+ "rstrip": false,
246
+ "normalized": true,
247
+ "special": false
248
+ },
249
+ {
250
+ "id": 50283,
251
+ "content": "<|extratoken_27|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": true,
256
+ "special": false
257
+ },
258
+ {
259
+ "id": 50284,
260
+ "content": "<|extratoken_28|>",
261
+ "single_word": false,
262
+ "lstrip": false,
263
+ "rstrip": false,
264
+ "normalized": true,
265
+ "special": false
266
+ },
267
+ {
268
+ "id": 50285,
269
+ "content": "<|extratoken_29|>",
270
+ "single_word": false,
271
+ "lstrip": false,
272
+ "rstrip": false,
273
+ "normalized": true,
274
+ "special": false
275
+ },
276
+ {
277
+ "id": 50286,
278
+ "content": "<|extratoken_30|>",
279
+ "single_word": false,
280
+ "lstrip": false,
281
+ "rstrip": false,
282
+ "normalized": true,
283
+ "special": false
284
+ },
285
+ {
286
+ "id": 50287,
287
+ "content": "<|extratoken_31|>",
288
+ "single_word": false,
289
+ "lstrip": false,
290
+ "rstrip": false,
291
+ "normalized": true,
292
+ "special": false
293
+ },
294
+ {
295
+ "id": 50288,
296
+ "content": "<|extratoken_32|>",
297
+ "single_word": false,
298
+ "lstrip": false,
299
+ "rstrip": false,
300
+ "normalized": true,
301
+ "special": false
302
+ },
303
+ {
304
+ "id": 50289,
305
+ "content": "<|extratoken_33|>",
306
+ "single_word": false,
307
+ "lstrip": false,
308
+ "rstrip": false,
309
+ "normalized": true,
310
+ "special": false
311
+ },
312
+ {
313
+ "id": 50290,
314
+ "content": "<|extratoken_34|>",
315
+ "single_word": false,
316
+ "lstrip": false,
317
+ "rstrip": false,
318
+ "normalized": true,
319
+ "special": false
320
+ },
321
+ {
322
+ "id": 50291,
323
+ "content": "<|extratoken_35|>",
324
+ "single_word": false,
325
+ "lstrip": false,
326
+ "rstrip": false,
327
+ "normalized": true,
328
+ "special": false
329
+ },
330
+ {
331
+ "id": 50292,
332
+ "content": "<|extratoken_36|>",
333
+ "single_word": false,
334
+ "lstrip": false,
335
+ "rstrip": false,
336
+ "normalized": true,
337
+ "special": false
338
+ },
339
+ {
340
+ "id": 50293,
341
+ "content": "<|extratoken_37|>",
342
+ "single_word": false,
343
+ "lstrip": false,
344
+ "rstrip": false,
345
+ "normalized": true,
346
+ "special": false
347
+ },
348
+ {
349
+ "id": 50294,
350
+ "content": "<|extratoken_38|>",
351
+ "single_word": false,
352
+ "lstrip": false,
353
+ "rstrip": false,
354
+ "normalized": true,
355
+ "special": false
356
+ },
357
+ {
358
+ "id": 50295,
359
+ "content": "<|extratoken_39|>",
360
+ "single_word": false,
361
+ "lstrip": false,
362
+ "rstrip": false,
363
+ "normalized": true,
364
+ "special": false
365
+ },
366
+ {
367
+ "id": 50296,
368
+ "content": "<|extratoken_40|>",
369
+ "single_word": false,
370
+ "lstrip": false,
371
+ "rstrip": false,
372
+ "normalized": true,
373
+ "special": false
374
+ },
375
+ {
376
+ "id": 50297,
377
+ "content": "<|extratoken_41|>",
378
+ "single_word": false,
379
+ "lstrip": false,
380
+ "rstrip": false,
381
+ "normalized": true,
382
+ "special": false
383
+ },
384
+ {
385
+ "id": 50298,
386
+ "content": "<|extratoken_42|>",
387
+ "single_word": false,
388
+ "lstrip": false,
389
+ "rstrip": false,
390
+ "normalized": true,
391
+ "special": false
392
+ },
393
+ {
394
+ "id": 50299,
395
+ "content": "<|extratoken_43|>",
396
+ "single_word": false,
397
+ "lstrip": false,
398
+ "rstrip": false,
399
+ "normalized": true,
400
+ "special": false
401
+ },
402
+ {
403
+ "id": 50300,
404
+ "content": "<|extratoken_44|>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": true,
409
+ "special": false
410
+ },
411
+ {
412
+ "id": 50301,
413
+ "content": "<|extratoken_45|>",
414
+ "single_word": false,
415
+ "lstrip": false,
416
+ "rstrip": false,
417
+ "normalized": true,
418
+ "special": false
419
+ },
420
+ {
421
+ "id": 50302,
422
+ "content": "<|extratoken_46|>",
423
+ "single_word": false,
424
+ "lstrip": false,
425
+ "rstrip": false,
426
+ "normalized": true,
427
+ "special": false
428
+ },
429
+ {
430
+ "id": 50303,
431
+ "content": "<|extratoken_47|>",
432
+ "single_word": false,
433
+ "lstrip": false,
434
+ "rstrip": false,
435
+ "normalized": true,
436
+ "special": false
437
+ },
438
+ {
439
+ "id": 50304,
440
+ "content": "<|extratoken_48|>",
441
+ "single_word": false,
442
+ "lstrip": false,
443
+ "rstrip": false,
444
+ "normalized": true,
445
+ "special": false
446
+ },
447
+ {
448
+ "id": 50305,
449
+ "content": "<|extratoken_49|>",
450
+ "single_word": false,
451
+ "lstrip": false,
452
+ "rstrip": false,
453
+ "normalized": true,
454
+ "special": false
455
+ },
456
+ {
457
+ "id": 50306,
458
+ "content": "<|extratoken_50|>",
459
+ "single_word": false,
460
+ "lstrip": false,
461
+ "rstrip": false,
462
+ "normalized": true,
463
+ "special": false
464
+ },
465
+ {
466
+ "id": 50307,
467
+ "content": "<|extratoken_51|>",
468
+ "single_word": false,
469
+ "lstrip": false,
470
+ "rstrip": false,
471
+ "normalized": true,
472
+ "special": false
473
+ },
474
+ {
475
+ "id": 50308,
476
+ "content": "<|extratoken_52|>",
477
+ "single_word": false,
478
+ "lstrip": false,
479
+ "rstrip": false,
480
+ "normalized": true,
481
+ "special": false
482
+ },
483
+ {
484
+ "id": 50309,
485
+ "content": "<|extratoken_53|>",
486
+ "single_word": false,
487
+ "lstrip": false,
488
+ "rstrip": false,
489
+ "normalized": true,
490
+ "special": false
491
+ },
492
+ {
493
+ "id": 50310,
494
+ "content": "<|extratoken_54|>",
495
+ "single_word": false,
496
+ "lstrip": false,
497
+ "rstrip": false,
498
+ "normalized": true,
499
+ "special": false
500
+ },
501
+ {
502
+ "id": 50311,
503
+ "content": "<|extratoken_55|>",
504
+ "single_word": false,
505
+ "lstrip": false,
506
+ "rstrip": false,
507
+ "normalized": true,
508
+ "special": false
509
+ },
510
+ {
511
+ "id": 50312,
512
+ "content": "<|extratoken_56|>",
513
+ "single_word": false,
514
+ "lstrip": false,
515
+ "rstrip": false,
516
+ "normalized": true,
517
+ "special": false
518
+ },
519
+ {
520
+ "id": 50313,
521
+ "content": "<|extratoken_57|>",
522
+ "single_word": false,
523
+ "lstrip": false,
524
+ "rstrip": false,
525
+ "normalized": true,
526
+ "special": false
527
+ },
528
+ {
529
+ "id": 50314,
530
+ "content": "<|extratoken_58|>",
531
+ "single_word": false,
532
+ "lstrip": false,
533
+ "rstrip": false,
534
+ "normalized": true,
535
+ "special": false
536
+ },
537
+ {
538
+ "id": 50315,
539
+ "content": "<|extratoken_59|>",
540
+ "single_word": false,
541
+ "lstrip": false,
542
+ "rstrip": false,
543
+ "normalized": true,
544
+ "special": false
545
+ },
546
+ {
547
+ "id": 50316,
548
+ "content": "<|extratoken_60|>",
549
+ "single_word": false,
550
+ "lstrip": false,
551
+ "rstrip": false,
552
+ "normalized": true,
553
+ "special": false
554
+ },
555
+ {
556
+ "id": 50317,
557
+ "content": "<|extratoken_61|>",
558
+ "single_word": false,
559
+ "lstrip": false,
560
+ "rstrip": false,
561
+ "normalized": true,
562
+ "special": false
563
+ },
564
+ {
565
+ "id": 50318,
566
+ "content": "<|extratoken_62|>",
567
+ "single_word": false,
568
+ "lstrip": false,
569
+ "rstrip": false,
570
+ "normalized": true,
571
+ "special": false
572
+ },
573
+ {
574
+ "id": 50319,
575
+ "content": "<|extratoken_63|>",
576
+ "single_word": false,
577
+ "lstrip": false,
578
+ "rstrip": false,
579
+ "normalized": true,
580
+ "special": false
581
+ },
582
+ {
583
+ "id": 50320,
584
+ "content": "<|extratoken_64|>",
585
+ "single_word": false,
586
+ "lstrip": false,
587
+ "rstrip": false,
588
+ "normalized": true,
589
+ "special": false
590
+ },
591
+ {
592
+ "id": 50321,
593
+ "content": "<|extratoken_65|>",
594
+ "single_word": false,
595
+ "lstrip": false,
596
+ "rstrip": false,
597
+ "normalized": true,
598
+ "special": false
599
+ },
600
+ {
601
+ "id": 50322,
602
+ "content": "<|extratoken_66|>",
603
+ "single_word": false,
604
+ "lstrip": false,
605
+ "rstrip": false,
606
+ "normalized": true,
607
+ "special": false
608
+ },
609
+ {
610
+ "id": 50323,
611
+ "content": "<|extratoken_67|>",
612
+ "single_word": false,
613
+ "lstrip": false,
614
+ "rstrip": false,
615
+ "normalized": true,
616
+ "special": false
617
+ },
618
+ {
619
+ "id": 50324,
620
+ "content": "<|extratoken_68|>",
621
+ "single_word": false,
622
+ "lstrip": false,
623
+ "rstrip": false,
624
+ "normalized": true,
625
+ "special": false
626
+ },
627
+ {
628
+ "id": 50325,
629
+ "content": "<|extratoken_69|>",
630
+ "single_word": false,
631
+ "lstrip": false,
632
+ "rstrip": false,
633
+ "normalized": true,
634
+ "special": false
635
+ },
636
+ {
637
+ "id": 50326,
638
+ "content": "<|extratoken_70|>",
639
+ "single_word": false,
640
+ "lstrip": false,
641
+ "rstrip": false,
642
+ "normalized": true,
643
+ "special": false
644
+ },
645
+ {
646
+ "id": 50327,
647
+ "content": "<|extratoken_71|>",
648
+ "single_word": false,
649
+ "lstrip": false,
650
+ "rstrip": false,
651
+ "normalized": true,
652
+ "special": false
653
+ },
654
+ {
655
+ "id": 50328,
656
+ "content": "<|extratoken_72|>",
657
+ "single_word": false,
658
+ "lstrip": false,
659
+ "rstrip": false,
660
+ "normalized": true,
661
+ "special": false
662
+ },
663
+ {
664
+ "id": 50329,
665
+ "content": "<|extratoken_73|>",
666
+ "single_word": false,
667
+ "lstrip": false,
668
+ "rstrip": false,
669
+ "normalized": true,
670
+ "special": false
671
+ },
672
+ {
673
+ "id": 50330,
674
+ "content": "<|extratoken_74|>",
675
+ "single_word": false,
676
+ "lstrip": false,
677
+ "rstrip": false,
678
+ "normalized": true,
679
+ "special": false
680
+ },
681
+ {
682
+ "id": 50331,
683
+ "content": "<|extratoken_75|>",
684
+ "single_word": false,
685
+ "lstrip": false,
686
+ "rstrip": false,
687
+ "normalized": true,
688
+ "special": false
689
+ },
690
+ {
691
+ "id": 50332,
692
+ "content": "<|extratoken_76|>",
693
+ "single_word": false,
694
+ "lstrip": false,
695
+ "rstrip": false,
696
+ "normalized": true,
697
+ "special": false
698
+ },
699
+ {
700
+ "id": 50333,
701
+ "content": "<|extratoken_77|>",
702
+ "single_word": false,
703
+ "lstrip": false,
704
+ "rstrip": false,
705
+ "normalized": true,
706
+ "special": false
707
+ },
708
+ {
709
+ "id": 50334,
710
+ "content": "<|extratoken_78|>",
711
+ "single_word": false,
712
+ "lstrip": false,
713
+ "rstrip": false,
714
+ "normalized": true,
715
+ "special": false
716
+ },
717
+ {
718
+ "id": 50335,
719
+ "content": "<|extratoken_79|>",
720
+ "single_word": false,
721
+ "lstrip": false,
722
+ "rstrip": false,
723
+ "normalized": true,
724
+ "special": false
725
+ },
726
+ {
727
+ "id": 50336,
728
+ "content": "<|extratoken_80|>",
729
+ "single_word": false,
730
+ "lstrip": false,
731
+ "rstrip": false,
732
+ "normalized": true,
733
+ "special": false
734
+ },
735
+ {
736
+ "id": 50337,
737
+ "content": "<|extratoken_81|>",
738
+ "single_word": false,
739
+ "lstrip": false,
740
+ "rstrip": false,
741
+ "normalized": true,
742
+ "special": false
743
+ },
744
+ {
745
+ "id": 50338,
746
+ "content": "<|extratoken_82|>",
747
+ "single_word": false,
748
+ "lstrip": false,
749
+ "rstrip": false,
750
+ "normalized": true,
751
+ "special": false
752
+ },
753
+ {
754
+ "id": 50339,
755
+ "content": "<|extratoken_83|>",
756
+ "single_word": false,
757
+ "lstrip": false,
758
+ "rstrip": false,
759
+ "normalized": true,
760
+ "special": false
761
+ },
762
+ {
763
+ "id": 50340,
764
+ "content": "<|extratoken_84|>",
765
+ "single_word": false,
766
+ "lstrip": false,
767
+ "rstrip": false,
768
+ "normalized": true,
769
+ "special": false
770
+ },
771
+ {
772
+ "id": 50341,
773
+ "content": "<|extratoken_85|>",
774
+ "single_word": false,
775
+ "lstrip": false,
776
+ "rstrip": false,
777
+ "normalized": true,
778
+ "special": false
779
+ },
780
+ {
781
+ "id": 50342,
782
+ "content": "<|extratoken_86|>",
783
+ "single_word": false,
784
+ "lstrip": false,
785
+ "rstrip": false,
786
+ "normalized": true,
787
+ "special": false
788
+ },
789
+ {
790
+ "id": 50343,
791
+ "content": "<|extratoken_87|>",
792
+ "single_word": false,
793
+ "lstrip": false,
794
+ "rstrip": false,
795
+ "normalized": true,
796
+ "special": false
797
+ },
798
+ {
799
+ "id": 50344,
800
+ "content": "<|extratoken_88|>",
801
+ "single_word": false,
802
+ "lstrip": false,
803
+ "rstrip": false,
804
+ "normalized": true,
805
+ "special": false
806
+ },
807
+ {
808
+ "id": 50345,
809
+ "content": "<|extratoken_89|>",
810
+ "single_word": false,
811
+ "lstrip": false,
812
+ "rstrip": false,
813
+ "normalized": true,
814
+ "special": false
815
+ },
816
+ {
817
+ "id": 50346,
818
+ "content": "<|extratoken_90|>",
819
+ "single_word": false,
820
+ "lstrip": false,
821
+ "rstrip": false,
822
+ "normalized": true,
823
+ "special": false
824
+ },
825
+ {
826
+ "id": 50347,
827
+ "content": "<|extratoken_91|>",
828
+ "single_word": false,
829
+ "lstrip": false,
830
+ "rstrip": false,
831
+ "normalized": true,
832
+ "special": false
833
+ },
834
+ {
835
+ "id": 50348,
836
+ "content": "<|extratoken_92|>",
837
+ "single_word": false,
838
+ "lstrip": false,
839
+ "rstrip": false,
840
+ "normalized": true,
841
+ "special": false
842
+ },
843
+ {
844
+ "id": 50349,
845
+ "content": "<|extratoken_93|>",
846
+ "single_word": false,
847
+ "lstrip": false,
848
+ "rstrip": false,
849
+ "normalized": true,
850
+ "special": false
851
+ },
852
+ {
853
+ "id": 50350,
854
+ "content": "<|extratoken_94|>",
855
+ "single_word": false,
856
+ "lstrip": false,
857
+ "rstrip": false,
858
+ "normalized": true,
859
+ "special": false
860
+ },
861
+ {
862
+ "id": 50351,
863
+ "content": "<|extratoken_95|>",
864
+ "single_word": false,
865
+ "lstrip": false,
866
+ "rstrip": false,
867
+ "normalized": true,
868
+ "special": false
869
+ },
870
+ {
871
+ "id": 50352,
872
+ "content": "<|extratoken_96|>",
873
+ "single_word": false,
874
+ "lstrip": false,
875
+ "rstrip": false,
876
+ "normalized": true,
877
+ "special": false
878
+ },
879
+ {
880
+ "id": 50353,
881
+ "content": "<|extratoken_97|>",
882
+ "single_word": false,
883
+ "lstrip": false,
884
+ "rstrip": false,
885
+ "normalized": true,
886
+ "special": false
887
+ },
888
+ {
889
+ "id": 50354,
890
+ "content": "<|extratoken_98|>",
891
+ "single_word": false,
892
+ "lstrip": false,
893
+ "rstrip": false,
894
+ "normalized": true,
895
+ "special": false
896
+ },
897
+ {
898
+ "id": 50355,
899
+ "content": "<|extratoken_99|>",
900
+ "single_word": false,
901
+ "lstrip": false,
902
+ "rstrip": false,
903
+ "normalized": true,
904
+ "special": false
905
+ },
906
+ {
907
+ "id": 50356,
908
+ "content": "<|extratoken_100|>",
909
+ "single_word": false,
910
+ "lstrip": false,
911
+ "rstrip": false,
912
+ "normalized": true,
913
+ "special": false
914
+ },
915
+ {
916
+ "id": 50357,
917
+ "content": "<|extratoken_101|>",
918
+ "single_word": false,
919
+ "lstrip": false,
920
+ "rstrip": false,
921
+ "normalized": true,
922
+ "special": false
923
+ },
924
+ {
925
+ "id": 50358,
926
+ "content": "<|extratoken_102|>",
927
+ "single_word": false,
928
+ "lstrip": false,
929
+ "rstrip": false,
930
+ "normalized": true,
931
+ "special": false
932
+ },
933
+ {
934
+ "id": 50359,
935
+ "content": "<|extratoken_103|>",
936
+ "single_word": false,
937
+ "lstrip": false,
938
+ "rstrip": false,
939
+ "normalized": true,
940
+ "special": false
941
+ },
942
+ {
943
+ "id": 50360,
944
+ "content": "<|extratoken_104|>",
945
+ "single_word": false,
946
+ "lstrip": false,
947
+ "rstrip": false,
948
+ "normalized": true,
949
+ "special": false
950
+ },
951
+ {
952
+ "id": 50361,
953
+ "content": "<|extratoken_105|>",
954
+ "single_word": false,
955
+ "lstrip": false,
956
+ "rstrip": false,
957
+ "normalized": true,
958
+ "special": false
959
+ },
960
+ {
961
+ "id": 50362,
962
+ "content": "<|extratoken_106|>",
963
+ "single_word": false,
964
+ "lstrip": false,
965
+ "rstrip": false,
966
+ "normalized": true,
967
+ "special": false
968
+ },
969
+ {
970
+ "id": 50363,
971
+ "content": "<|extratoken_107|>",
972
+ "single_word": false,
973
+ "lstrip": false,
974
+ "rstrip": false,
975
+ "normalized": true,
976
+ "special": false
977
+ },
978
+ {
979
+ "id": 50364,
980
+ "content": "<|extratoken_108|>",
981
+ "single_word": false,
982
+ "lstrip": false,
983
+ "rstrip": false,
984
+ "normalized": true,
985
+ "special": false
986
+ },
987
+ {
988
+ "id": 50365,
989
+ "content": "<|extratoken_109|>",
990
+ "single_word": false,
991
+ "lstrip": false,
992
+ "rstrip": false,
993
+ "normalized": true,
994
+ "special": false
995
+ },
996
+ {
997
+ "id": 50366,
998
+ "content": "<|extratoken_110|>",
999
+ "single_word": false,
1000
+ "lstrip": false,
1001
+ "rstrip": false,
1002
+ "normalized": true,
1003
+ "special": false
1004
+ },
1005
+ {
1006
+ "id": 50367,
1007
+ "content": "<|extratoken_111|>",
1008
+ "single_word": false,
1009
+ "lstrip": false,
1010
+ "rstrip": false,
1011
+ "normalized": true,
1012
+ "special": false
1013
+ },
1014
+ {
1015
+ "id": 50368,
1016
+ "content": "<|extratoken_112|>",
1017
+ "single_word": false,
1018
+ "lstrip": false,
1019
+ "rstrip": false,
1020
+ "normalized": true,
1021
+ "special": false
1022
+ },
1023
+ {
1024
+ "id": 50369,
1025
+ "content": "<|extratoken_113|>",
1026
+ "single_word": false,
1027
+ "lstrip": false,
1028
+ "rstrip": false,
1029
+ "normalized": true,
1030
+ "special": false
1031
+ },
1032
+ {
1033
+ "id": 50370,
1034
+ "content": "<|extratoken_114|>",
1035
+ "single_word": false,
1036
+ "lstrip": false,
1037
+ "rstrip": false,
1038
+ "normalized": true,
1039
+ "special": false
1040
+ },
1041
+ {
1042
+ "id": 50371,
1043
+ "content": "<|extratoken_115|>",
1044
+ "single_word": false,
1045
+ "lstrip": false,
1046
+ "rstrip": false,
1047
+ "normalized": true,
1048
+ "special": false
1049
+ },
1050
+ {
1051
+ "id": 50372,
1052
+ "content": "<|extratoken_116|>",
1053
+ "single_word": false,
1054
+ "lstrip": false,
1055
+ "rstrip": false,
1056
+ "normalized": true,
1057
+ "special": false
1058
+ },
1059
+ {
1060
+ "id": 50373,
1061
+ "content": "<|extratoken_117|>",
1062
+ "single_word": false,
1063
+ "lstrip": false,
1064
+ "rstrip": false,
1065
+ "normalized": true,
1066
+ "special": false
1067
+ },
1068
+ {
1069
+ "id": 50374,
1070
+ "content": "<|extratoken_118|>",
1071
+ "single_word": false,
1072
+ "lstrip": false,
1073
+ "rstrip": false,
1074
+ "normalized": true,
1075
+ "special": false
1076
+ },
1077
+ {
1078
+ "id": 50375,
1079
+ "content": "<|extratoken_119|>",
1080
+ "single_word": false,
1081
+ "lstrip": false,
1082
+ "rstrip": false,
1083
+ "normalized": true,
1084
+ "special": false
1085
+ },
1086
+ {
1087
+ "id": 50376,
1088
+ "content": "<|extratoken_120|>",
1089
+ "single_word": false,
1090
+ "lstrip": false,
1091
+ "rstrip": false,
1092
+ "normalized": true,
1093
+ "special": false
1094
+ },
1095
+ {
1096
+ "id": 50377,
1097
+ "content": "<|extratoken_121|>",
1098
+ "single_word": false,
1099
+ "lstrip": false,
1100
+ "rstrip": false,
1101
+ "normalized": true,
1102
+ "special": false
1103
+ },
1104
+ {
1105
+ "id": 50378,
1106
+ "content": "<|extratoken_122|>",
1107
+ "single_word": false,
1108
+ "lstrip": false,
1109
+ "rstrip": false,
1110
+ "normalized": true,
1111
+ "special": false
1112
+ },
1113
+ {
1114
+ "id": 50379,
1115
+ "content": "<|extratoken_123|>",
1116
+ "single_word": false,
1117
+ "lstrip": false,
1118
+ "rstrip": false,
1119
+ "normalized": true,
1120
+ "special": false
1121
+ },
1122
+ {
1123
+ "id": 50380,
1124
+ "content": "<|extratoken_124|>",
1125
+ "single_word": false,
1126
+ "lstrip": false,
1127
+ "rstrip": false,
1128
+ "normalized": true,
1129
+ "special": false
1130
+ },
1131
+ {
1132
+ "id": 50381,
1133
+ "content": "<|extratoken_125|>",
1134
+ "single_word": false,
1135
+ "lstrip": false,
1136
+ "rstrip": false,
1137
+ "normalized": true,
1138
+ "special": false
1139
+ },
1140
+ {
1141
+ "id": 50382,
1142
+ "content": "<|extratoken_126|>",
1143
+ "single_word": false,
1144
+ "lstrip": false,
1145
+ "rstrip": false,
1146
+ "normalized": true,
1147
+ "special": false
1148
+ },
1149
+ {
1150
+ "id": 50383,
1151
+ "content": "<|extratoken_127|>",
1152
+ "single_word": false,
1153
+ "lstrip": false,
1154
+ "rstrip": false,
1155
+ "normalized": true,
1156
+ "special": false
1157
+ },
1158
+ {
1159
+ "id": 50384,
1160
+ "content": "<|extratoken_128|>",
1161
+ "single_word": false,
1162
+ "lstrip": false,
1163
+ "rstrip": false,
1164
+ "normalized": true,
1165
+ "special": false
1166
+ },
1167
+ {
1168
+ "id": 50385,
1169
+ "content": "<|extratoken_129|>",
1170
+ "single_word": false,
1171
+ "lstrip": false,
1172
+ "rstrip": false,
1173
+ "normalized": true,
1174
+ "special": false
1175
+ },
1176
+ {
1177
+ "id": 50386,
1178
+ "content": "<|extratoken_130|>",
1179
+ "single_word": false,
1180
+ "lstrip": false,
1181
+ "rstrip": false,
1182
+ "normalized": true,
1183
+ "special": false
1184
+ },
1185
+ {
1186
+ "id": 50387,
1187
+ "content": "<|extratoken_131|>",
1188
+ "single_word": false,
1189
+ "lstrip": false,
1190
+ "rstrip": false,
1191
+ "normalized": true,
1192
+ "special": false
1193
+ },
1194
+ {
1195
+ "id": 50388,
1196
+ "content": "<|extratoken_132|>",
1197
+ "single_word": false,
1198
+ "lstrip": false,
1199
+ "rstrip": false,
1200
+ "normalized": true,
1201
+ "special": false
1202
+ },
1203
+ {
1204
+ "id": 50389,
1205
+ "content": "<|extratoken_133|>",
1206
+ "single_word": false,
1207
+ "lstrip": false,
1208
+ "rstrip": false,
1209
+ "normalized": true,
1210
+ "special": false
1211
+ },
1212
+ {
1213
+ "id": 50390,
1214
+ "content": "<|extratoken_134|>",
1215
+ "single_word": false,
1216
+ "lstrip": false,
1217
+ "rstrip": false,
1218
+ "normalized": true,
1219
+ "special": false
1220
+ },
1221
+ {
1222
+ "id": 50391,
1223
+ "content": "<|extratoken_135|>",
1224
+ "single_word": false,
1225
+ "lstrip": false,
1226
+ "rstrip": false,
1227
+ "normalized": true,
1228
+ "special": false
1229
+ },
1230
+ {
1231
+ "id": 50392,
1232
+ "content": "<|extratoken_136|>",
1233
+ "single_word": false,
1234
+ "lstrip": false,
1235
+ "rstrip": false,
1236
+ "normalized": true,
1237
+ "special": false
1238
+ },
1239
+ {
1240
+ "id": 50393,
1241
+ "content": "<|extratoken_137|>",
1242
+ "single_word": false,
1243
+ "lstrip": false,
1244
+ "rstrip": false,
1245
+ "normalized": true,
1246
+ "special": false
1247
+ },
1248
+ {
1249
+ "id": 50394,
1250
+ "content": "<|extratoken_138|>",
1251
+ "single_word": false,
1252
+ "lstrip": false,
1253
+ "rstrip": false,
1254
+ "normalized": true,
1255
+ "special": false
1256
+ },
1257
+ {
1258
+ "id": 50395,
1259
+ "content": "<|extratoken_139|>",
1260
+ "single_word": false,
1261
+ "lstrip": false,
1262
+ "rstrip": false,
1263
+ "normalized": true,
1264
+ "special": false
1265
+ },
1266
+ {
1267
+ "id": 50396,
1268
+ "content": "<|extratoken_140|>",
1269
+ "single_word": false,
1270
+ "lstrip": false,
1271
+ "rstrip": false,
1272
+ "normalized": true,
1273
+ "special": false
1274
+ },
1275
+ {
1276
+ "id": 50397,
1277
+ "content": "<|extratoken_141|>",
1278
+ "single_word": false,
1279
+ "lstrip": false,
1280
+ "rstrip": false,
1281
+ "normalized": true,
1282
+ "special": false
1283
+ },
1284
+ {
1285
+ "id": 50398,
1286
+ "content": "<|extratoken_142|>",
1287
+ "single_word": false,
1288
+ "lstrip": false,
1289
+ "rstrip": false,
1290
+ "normalized": true,
1291
+ "special": false
1292
+ },
1293
+ {
1294
+ "id": 50399,
1295
+ "content": "<|extratoken_143|>",
1296
+ "single_word": false,
1297
+ "lstrip": false,
1298
+ "rstrip": false,
1299
+ "normalized": true,
1300
+ "special": false
1301
  }
1302
  ],
1303
  "normalizer": null,
tokenizer_config.json CHANGED
@@ -1 +1,33 @@
1
- {"unk_token": "<|endoftext|>", "bos_token": "<|endoftext|>", "eos_token": "<|endoftext|>", "add_prefix_space": false, "model_max_length": 2048, "special_tokens_map_file": null, "name_or_path": "bertin-project/bertin-gpt-j-6B", "tokenizer_class": "GPT2Tokenizer"}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "bos_token": {
5
+ "__type": "AddedToken",
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "__type": "AddedToken",
14
+ "content": "<|endoftext|>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "errors": "replace",
21
+ "model_max_length": 2048,
22
+ "pad_token": null,
23
+ "special_tokens_map_file": null,
24
+ "tokenizer_class": "GPT2Tokenizer",
25
+ "unk_token": {
26
+ "__type": "AddedToken",
27
+ "content": "<|endoftext|>",
28
+ "lstrip": false,
29
+ "normalized": true,
30
+ "rstrip": false,
31
+ "single_word": false
32
+ }
33
+ }